METR Q4 2026 TH2 - Minecraft Bot: leaderboard

METR's Q4 2026 capability update (20 November 2026): mean score from 0 to 1 on one task of TH2, METR's new long-task suite. The agent writes an autonomous bot that has to beat Minecraft on hidden worlds; the score rises with the checkpoints the bot reaches. Higher is better.

Metric: Mean Score (0-1). Source: metr.org. Saturation forecast: Around August 2028. 15 models tracked. Updated 21 Nov 2026.

Top models

#ModelScoreOverall rank
1GPT-6 Astra0.175#10
2Claude Opus 5.50.175#9
3Claude Fable 50.1225#33
4Claude Opus 4.80.1075#65
5Claude Opus 4.60.07#113
6Claude Opus 4.70.07#85
7GPT-5.6 Sol0.07#37
8Claude Opus 50.07#26
9Claude Fable 5.10.07#20
10GPT-5.50.055#54
11Claude Opus 4.50.055#160
12GPT-5.40.02#135
13GPT-4o0#751
14GPT-50#178
15O10#403

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=metr-q4-2026-th2-minecraft-bot · How It Works · Data refreshed daily, snapshot 2026-11-21.